Naomi Saphra

@nsaphra

Waiting on a robot body. All opinions are universal and held by both employers and family. Now a dedicated grok hate account. (I post more elsewhere.)

following
followers

Interpretability work on grammatical inflection across languages slated for COLM

A researcher says Isabella Gidi led the work and a poster was scheduled for October 6.

1 Source, 16d ago, first seen 16d ago

Naomi Saphra Praises Ziv Ravid's LLM-Free Writing

Reply commends Ziv Ravid for writing that stayed coherent without an LLM.

1 Source, 48d ago, first seen 48d ago

Paul Graham Says 1980 View Would Call Current Models AGI

Academics and investors reply that housebots and game skills remain missing.

12 Sources, 71d ago, first seen 71d ago

Naomi Saphra Writes on AI and the Uncanny

Researcher Naomi Saphra shares an essay on dissociation triggered by realistic AI outputs.

8 Sources, 72d ago, first seen 72d ago

GoodfireAI Makes Silico Platform Publicly Available

The AI interpretability company announces access to its research tool.

32 Sources, 77d ago, first seen 77d ago

Featured in

Interpretability work on grammatical inflection across languages slated for COLM

Naomi Saphra Praises Ziv Ravid's LLM-Free Writing

Paul Graham Says 1980 View Would Call Current Models AGI

Naomi Saphra Writes on AI and the Uncanny

GoodfireAI Makes Silico Platform Publicly Available

Featured in

Interpretability work on grammatical inflection across languages slated for COLM

Naomi Saphra Praises Ziv Ravid's LLM-Free Writing

Paul Graham Says 1980 View Would Call Current Models AGI

Naomi Saphra Writes on AI and the Uncanny

GoodfireAI Makes Silico Platform Publicly Available